Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Leuconoe/ryubing-mcp --skill nsw-workspace-cleanupgit clone --depth 1 https://github.com/Leuconoe/ryubing-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/leuconoe/ryubing-mcp/nsw-workspace-cleanup)<a href="https://agentmods.dev/skills/leuconoe/ryubing-mcp/nsw-workspace-cleanup"><img src="https://agentmods.dev/badge/skills/leuconoe/ryubing-mcp/nsw-workspace-cleanup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/leuconoe/ryubing-mcp/nsw-workspace-cleanup"><img src="https://agentmods.dev/badge/skills/leuconoe/ryubing-mcp/nsw-workspace-cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.00990 |
| Opus 5 | $0.00042 | $0.00495 |
| Sonnet 5 | $0.00017 | $0.00198 |
| Haiku 4.5 | $0.00008 | $0.00099 |
Grade A, and why
nsw-workspace-cleanup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NSW workspace cleanup
Generate a reviewed cleanup plan for Ryubing and Eden together. Do not infer
ownership or deletion eligibility from names such as tmp, copy, session,
old, or a timestamp. Treat handoff history and emulator ownership manifests as
the primary evidence.
Read references/handoff-classification.md before classifying any artifact or session.
Establish scope
- Resolve each repository root, title root, project root, Ryubing session root, and Eden session root to a literal absolute path.
- Locate the relevant
HANDOFF.md,handoff/**/*.md, and title-localWORK_LOG.mdfiles. Read every selected handoff document completely. - Record the exact title/application ID and project ID. Stop on cross-title or cross-project contradictions.
- Query both MCPs for live sessions and artifacts when their tools are available. Treat filesystem manifests as persisted evidence, not proof that a process is inactive.
Build a deterministic evidence snapshot
Run the bundled read-only collector with every relevant root. Repeat flags as needed:
node .\scripts\build-cleanup-context.mjs `
--root "E:\NSW\_titles\Title [0100000000000000]" `
--handoff "D:\workspace\____personal____\ryubing-mcp\HANDOFF.md" `
--handoff "D:\workspace\____personal____\eden-mcp\HANDOFF.md" `
--session-root "ryubing=E:\NSW\_tools\Ryubing\mcp-bridge-v0.1.0\sessions" `
--session-root "eden=E:\NSW\_tools\Eden\mcp-v0.4.0\sessions" `
--json
The collector never writes or deletes files. It inventories bounded metadata, indexes handoff references and status cues, validates Ryubing/Eden ownership manifests, checks recorded PIDs, and reports duplicate hashes for review. If the snapshot is truncated or has no handoff documents, do not issue removal steps.
Infer the current artifact chain
- Reconstruct each title's progression in chronological and dependency order: source -> candidate -> static QA -> emulator staging -> runtime evidence -> user review -> release.
- Correlate exact paths, hashes, title IDs, session IDs, patch names, and capture paths across both emulators. A reference from either emulator protects the artifact until its downstream purpose is resolved.
- Distinguish current/final artifacts from failed-but-still-diagnostic evidence.
FAIL,BLOCKED, andPENDINGdo not mean disposable. - Mark an artifact eligible only when the handoff explicitly supersedes or retires it, an exact replacement is preserved, no open investigation depends on it, and it is not active or the sole evidence for a claim.
- Treat unreferenced and duplicate artifacts as
REVIEW, never as automatic deletion candidates.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 89 lines · 83 tokens per session scan A e63a6c833636
nsw-workspace-cleanup is a skill published in the GitHub repository Leuconoe/ryubing-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 990 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
azure-ai-translation-text-py
Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.